Search
New Approach of the Recurrent Neural Network Training
Citation
Golovko, V. New Approach of the Recurrent Neural Network Training / V. Golovko, Y. Savitsky // International Conference on Neural Networks and Artificial Intelligence ICNNAI’99 = Международная конференция по нейронным сетям и искусственному интеллекту ICNNAI’99 : Proceedings, Brest, Belarus, 12–15 October 1999 / Brest Polytechnic Institute, Department of Computers and Laboratory of Artificial Neural Networks, Belarus Special Interest Group of International Neural NetWork Society, International Neural NetWork Society, Belarusian State University of Informatics and Radioelectronics (Belarus), Belarusian Academy of Sciences, Institute of Engineering Cybemetics (Belarus), Universidad Politechnica de Valencia (Spain), Institute of Computer Information Technologies (Ukraine, Ternopil) ; ed. V. Golovko. – Brest : BPI, 1999. – P. 32–35.Abstract
In this work the technique o f creation o f adapthre training algorithms for recurrent neural networks (RNN) is cortsidered. These algorithms have high convergence and accuracy on a comparison with traditional backpropagation. The original technique of calculation of an adaptive training step with use of steepest descent method is resulted. The features of calculation of an adapttve pitch for neural elements with recurrent connections are discussed. Are considered the neural units with various functions of activation, used in architectures neural systems of forecasting. The indicated computing experiments demonstrate advantage o f the developed RNN training methods.
Collection
Это произведение доступно по лицензии Creative Commons «Attribution-NonCommercial» («Атрибуция-Некоммерчески») 4.0 Всемирная.